Meta-Learning for Physically-Constrained Neural System Identification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chakrabarty, Ankush, Wichern, Gordon, Deshpande, Vedang M., Vinod, Abraham P., Berntorp, Karl, Laughman, Christopher R.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912183279943680
author Chakrabarty, Ankush
Wichern, Gordon
Deshpande, Vedang M.
Vinod, Abraham P.
Berntorp, Karl
Laughman, Christopher R.
author_facet Chakrabarty, Ankush
Wichern, Gordon
Deshpande, Vedang M.
Vinod, Abraham P.
Berntorp, Karl
Laughman, Christopher R.
contents We present a gradient-based meta-learning framework for rapid adaptation of neural state-space models (NSSMs) for black-box system identification. When applicable, we also incorporate domain-specific physical constraints to improve the accuracy of the NSSM. The major benefit of our approach is that instead of relying solely on data from a single target system, our framework utilizes data from a diverse set of source systems, enabling learning from limited target data, as well as with few online training iterations. Through benchmark examples, we demonstrate the potential of our approach, study the effect of fine-tuning subnetworks rather than full fine-tuning, and report real-world case studies to illustrate the practical application and generalizability of the approach to practical problems with physical-constraints. Specifically, we show that the meta-learned models result in improved downstream performance in model-based state estimation in indoor localization and energy systems.
format Preprint
id arxiv_https___arxiv_org_abs_2501_06167
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Meta-Learning for Physically-Constrained Neural System Identification
Chakrabarty, Ankush
Wichern, Gordon
Deshpande, Vedang M.
Vinod, Abraham P.
Berntorp, Karl
Laughman, Christopher R.
Machine Learning
Systems and Control
Optimization and Control
We present a gradient-based meta-learning framework for rapid adaptation of neural state-space models (NSSMs) for black-box system identification. When applicable, we also incorporate domain-specific physical constraints to improve the accuracy of the NSSM. The major benefit of our approach is that instead of relying solely on data from a single target system, our framework utilizes data from a diverse set of source systems, enabling learning from limited target data, as well as with few online training iterations. Through benchmark examples, we demonstrate the potential of our approach, study the effect of fine-tuning subnetworks rather than full fine-tuning, and report real-world case studies to illustrate the practical application and generalizability of the approach to practical problems with physical-constraints. Specifically, we show that the meta-learned models result in improved downstream performance in model-based state estimation in indoor localization and energy systems.
title Meta-Learning for Physically-Constrained Neural System Identification
topic Machine Learning
Systems and Control
Optimization and Control
url https://arxiv.org/abs/2501.06167